# Mixtral 8x22B vs Step 5 Preview

> Step 5 Preview is the stronger model overall, scoring 47.9 to 27.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/mixtral-8x22b-vs-step-5-preview
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Mixtral 8x22B scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 5 Preview leads 51.8 to 24.2.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $2 / $6 for Mixtral 8x22B.
- Step 5 Preview accepts more context: 1.02M tokens versus 64K.
- Mixtral 8x22B has downloadable open weights; the other is API-only.

## Snapshot

| | Mixtral 8x22B | Step 5 Preview |
|---|---|---|
| Provider | Mistral AI | StepFun |
| Noometry Index | 27.1 | 47.9 |
| Rank | 333 | 58 |
| Context | 64K | 1.02M |
| Input $/M | $2 | $1 |
| Output $/M | $6 | $2.70 |
| Weights | Open | Proprietary |

## Coding

- Mixtral 8x22B: 24.2 (#329)
- Step 5 Preview: 51.8 (#36)

| Benchmark | Mixtral 8x22B | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1166 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| WeirdML | 3.2% | — |
| BigCodeBench Instruct | 40.6% | — |
| BigCodeBench Complete | 50.2% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 64.3% | — |

## Agentic & Tool Use

- Mixtral 8x22B: 23.1 (#127)
- Step 5 Preview: —

| Benchmark | Mixtral 8x22B | Step 5 Preview |
|---|---|---|
| Cybench | 7.5% | — |

## Reasoning

- Mixtral 8x22B: 19.9 (#248)
- Step 5 Preview: 40.0 (#57)

| Benchmark | Mixtral 8x22B | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1150 | 1465 |
| CritPt | — | 20.9% |
| DTBench | 55.1% | — |
| Epoch Capabilities Index | 122.03 | — |
| ForecastBench | 56.3 | — |

## Math

- Mixtral 8x22B: 22.9 (#275)
- Step 5 Preview: 46.1 (#72)

| Benchmark | Mixtral 8x22B | Step 5 Preview |
|---|---|---|
| LMArena Math | 1184 | 1470 |
| ProofBench | — | 42% |
| Omni-MATH | 16.3% | — |
| MATH Level 5 | 24.2% | — |

## Knowledge

- Mixtral 8x22B: 15.1 (#293)
- Step 5 Preview: 41.2 (#112)

| Benchmark | Mixtral 8x22B | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1113 | 1470 |
| GPQA Diamond | 34.1% | — |
| MMLU-Pro | 46% | — |
| GPQA (HELM) | 33.4% | — |
| MMLU | 77.8% | — |

## Multimodal

- Mixtral 8x22B: —
- Step 5 Preview: 41.0 (#41)

| Benchmark | Mixtral 8x22B | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |

## Multilingual

- Mixtral 8x22B: 32.8 (#255)
- Step 5 Preview: 53.8 (#54)

| Benchmark | Mixtral 8x22B | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1128 | 1432 |
| LMArena Chinese | 1116 | 1519 |
| LMArena Russian | 1158 | 1436 |
| LMArena Spanish | 1151 | 1439 |
| LMArena French | 1166 | — |
| LMArena German | 1141 | — |
| LMArena Japanese | 1037 | — |
| LMArena Korean | 1057 | — |

## Instruction Following

- Mixtral 8x22B: 57.7 (#266)
- Step 5 Preview: 76.0 (#50)

| Benchmark | Mixtral 8x22B | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1147 | 1444 |
| IFEval | 72.4% | — |

## Long Context

- Mixtral 8x22B: 34.7 (#247)
- Step 5 Preview: 44.5 (#64)

| Benchmark | Mixtral 8x22B | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1144 | 1455 |

## Writing & Preference

- Mixtral 8x22B: 36.9 (#262)
- Step 5 Preview: 62.8 (#71)

| Benchmark | Mixtral 8x22B | Step 5 Preview |
|---|---|---|
| LMArena Text | 1162 | 1442 |
| LMArena Creative Writing | 1141 | 1410 |
| LMArena Multi-Turn | 1130 | 1447 |
| WildBench | 71.1% | — |

## FAQ

### Is Mixtral 8x22B better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 27.1 on the Noometry Index.

### Which is cheaper, Mixtral 8x22B or Step 5 Preview?

Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; Mixtral 8x22B lists at $2 and $6.

### Is Mixtral 8x22B or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 24.2 in the Noometry coding category.

### Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 64K.

### How many benchmarks do Mixtral 8x22B and Step 5 Preview share?

13 benchmarks have published results for both models. Mixtral 8x22B has 34 scored results on Noometry and Step 5 Preview has 18.